diff options
| author | Anton Blanchard <anton@samba.org> | 2013-10-14 21:03:58 +1100 |
|---|---|---|
| committer | Benjamin Herrenschmidt <benh@kernel.crashing.org> | 2013-10-30 16:02:28 +1100 |
| commit | ef1313deafb7baa6d3382044e962d5ad5e8c8dd6 (patch) | |
| tree | 30584552d8b2907bb8360a7d4e1cab28e3215585 /arch/powerpc/include/asm | |
| parent | 07fb41a7525539d7ad37c25f2a2689fd95a6ab68 (diff) | |
powerpc: Add VMX optimised xor for RAID5
Add a VMX optimised xor, used primarily for RAID5. On a POWER7 blade
this is a decent win:
32regs : 17932.800 MB/sec
altivec : 19724.800 MB/sec
The bigger gain is when the same test is run in SMT4 mode, as it
would if there was a lot of work going on:
8regs : 8377.600 MB/sec
altivec : 15801.600 MB/sec
I tested this against an array created without the patch, and also
verified it worked as expected on a little endian kernel.
[ Fix !CONFIG_ALTIVEC build -- BenH ]
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Diffstat (limited to 'arch/powerpc/include/asm')
| -rw-r--r-- | arch/powerpc/include/asm/xor.h | 67 |
1 files changed, 67 insertions, 0 deletions
diff --git a/arch/powerpc/include/asm/xor.h b/arch/powerpc/include/asm/xor.h index c82eb12a5b18..0abb97f3be10 100644 --- a/arch/powerpc/include/asm/xor.h +++ b/arch/powerpc/include/asm/xor.h @@ -1 +1,68 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * Copyright (C) IBM Corporation, 2012 + * + * Author: Anton Blanchard <anton@au.ibm.com> + */ +#ifndef _ASM_POWERPC_XOR_H +#define _ASM_POWERPC_XOR_H + +#ifdef CONFIG_ALTIVEC + +#include <asm/cputable.h> + +void xor_altivec_2(unsigned long bytes, unsigned long *v1_in, + unsigned long *v2_in); +void xor_altivec_3(unsigned long bytes, unsigned long *v1_in, + unsigned long *v2_in, unsigned long *v3_in); +void xor_altivec_4(unsigned long bytes, unsigned long *v1_in, + unsigned long *v2_in, unsigned long *v3_in, + unsigned long *v4_in); +void xor_altivec_5(unsigned long bytes, unsigned long *v1_in, + unsigned long *v2_in, unsigned long *v3_in, + unsigned long *v4_in, unsigned long *v5_in); + +static struct xor_block_template xor_block_altivec = { + .name = "altivec", + .do_2 = xor_altivec_2, + .do_3 = xor_altivec_3, + .do_4 = xor_altivec_4, + .do_5 = xor_altivec_5, +}; + +#define XOR_SPEED_ALTIVEC() \ + do { \ + if (cpu_has_feature(CPU_FTR_ALTIVEC)) \ + xor_speed(&xor_block_altivec); \ + } while (0) +#else +#define XOR_SPEED_ALTIVEC() +#endif + +/* Also try the generic routines. */ #include <asm-generic/xor.h> + +#undef XOR_TRY_TEMPLATES +#define XOR_TRY_TEMPLATES \ +do { \ + xor_speed(&xor_block_8regs); \ + xor_speed(&xor_block_8regs_p); \ + xor_speed(&xor_block_32regs); \ + xor_speed(&xor_block_32regs_p); \ + XOR_SPEED_ALTIVEC(); \ +} while (0) + +#endif /* _ASM_POWERPC_XOR_H */ |